library(tidyverse) # for data cleaning and plotting
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ──
## ✓ ggplot2 3.3.3 ✓ purrr 0.3.4
## ✓ tibble 3.0.5 ✓ dplyr 1.0.3
## ✓ tidyr 1.1.2 ✓ stringr 1.4.0
## ✓ readr 1.4.0 ✓ forcats 0.5.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(lubridate) # for date manipulation
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
library(openintro) # for the abbr2state() function
## Loading required package: airports
## Loading required package: cherryblossom
## Loading required package: usdata
library(palmerpenguins)# for Palmer penguin data
library(maps) # for map data
##
## Attaching package: 'maps'
## The following object is masked from 'package:purrr':
##
## map
library(ggmap) # for mapping points on maps
## Google's Terms of Service: https://cloud.google.com/maps-platform/terms/.
## Please cite ggmap if you use it! See citation("ggmap") for details.
library(gplots) # for col2hex() function
##
## Attaching package: 'gplots'
## The following object is masked from 'package:stats':
##
## lowess
library(RColorBrewer) # for color palettes
library(sf) # for working with spatial data
## Linking to GEOS 3.8.1, GDAL 3.1.4, PROJ 6.3.1
library(leaflet) # for highly customizable mapping
library(carData) # for Minneapolis police stops data
library(ggthemes) # for more themes (including theme_map())
theme_set(theme_minimal())
# Starbucks locations
Starbucks <- read_csv("https://www.macalester.edu/~ajohns24/Data/Starbucks.csv")
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## Brand = col_character(),
## `Store Number` = col_character(),
## `Store Name` = col_character(),
## `Ownership Type` = col_character(),
## `Street Address` = col_character(),
## City = col_character(),
## `State/Province` = col_character(),
## Country = col_character(),
## Postcode = col_character(),
## `Phone Number` = col_character(),
## Timezone = col_character(),
## Longitude = col_double(),
## Latitude = col_double()
## )
starbucks_us_by_state <- Starbucks %>%
filter(Country == "US") %>%
count(`State/Province`) %>%
mutate(state_name = str_to_lower(abbr2state(`State/Province`)))
# Lisa's favorite St. Paul places - example for you to create your own data
favorite_stp_by_lisa <- tibble(
place = c("Home", "Macalester College", "Adams Spanish Immersion",
"Spirit Gymnastics", "Bama & Bapa", "Now Bikes",
"Dance Spectrum", "Pizza Luce", "Brunson's"),
long = c(-93.1405743, -93.1712321, -93.1451796,
-93.1650563, -93.1542883, -93.1696608,
-93.1393172, -93.1524256, -93.0753863),
lat = c(44.950576, 44.9378965, 44.9237914,
44.9654609, 44.9295072, 44.9436813,
44.9399922, 44.9468848, 44.9700727)
)
#COVID-19 data from the New York Times
covid19 <- read_csv("https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-states.csv")
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## date = col_date(format = ""),
## state = col_character(),
## fips = col_character(),
## cases = col_double(),
## deaths = col_double()
## )
If you were not able to get set up on GitHub last week, go here and get set up first. Then, do the following (if you get stuck on a step, don’t worry, I will help! You can always get started on the homework and we can figure out the GitHub piece later):
keep_md: TRUE in the YAML heading. The .md file is a markdown (NOT R Markdown) file that is an interim step to creating the html file. They are displayed fairly nicely in GitHub, so we want to keep it and look at it there. Click the boxes next to these two files, commit changes (remember to include a commit message), and push them (green up arrow).Put your name at the top of the document.
For ALL graphs, you should include appropriate labels.
Feel free to change the default theme, which I currently have set to theme_minimal().
Use good coding practice. Read the short sections on good code with pipes and ggplot2. This is part of your grade!
When you are finished with ALL the exercises, uncomment the options at the top so your document looks nicer. Don’t do it before then, or else you might miss some important warnings and messages.
These exercises will reiterate what you learned in the “Mapping data with R” tutorial. If you haven’t gone through the tutorial yet, you should do that first.
ggmap)Starbucks locations to a world map. Add an aesthetic to the world map that sets the color of the points according to the ownership type. What, if anything, can you deduce from this visualization?world_map <- get_stamenmap(
bbox = c(left = -182.5, bottom = -60.4, right = 200.7, top = 81.8),
maptype = "terrain",
zoom = 2)
## Source : http://tile.stamen.com/terrain/2/-1/0.png
## Service Unavailable (HTTP 503). Failed to aquire tile /terrain/2/-1/0.png.
## Source : http://tile.stamen.com/terrain/2/0/0.png
## Source : http://tile.stamen.com/terrain/2/1/0.png
## Source : http://tile.stamen.com/terrain/2/2/0.png
## Source : http://tile.stamen.com/terrain/2/3/0.png
## Source : http://tile.stamen.com/terrain/2/4/0.png
## Not Found (HTTP 404). Failed to aquire tile /terrain/2/4/0.png.
## Source : http://tile.stamen.com/terrain/2/-1/1.png
## Service Unavailable (HTTP 503). Failed to aquire tile /terrain/2/-1/1.png.
## Source : http://tile.stamen.com/terrain/2/0/1.png
## Source : http://tile.stamen.com/terrain/2/1/1.png
## Source : http://tile.stamen.com/terrain/2/2/1.png
## Source : http://tile.stamen.com/terrain/2/3/1.png
## Source : http://tile.stamen.com/terrain/2/4/1.png
## Not Found (HTTP 404). Failed to aquire tile /terrain/2/4/1.png.
## Source : http://tile.stamen.com/terrain/2/-1/2.png
## Service Unavailable (HTTP 503). Failed to aquire tile /terrain/2/-1/2.png.
## Source : http://tile.stamen.com/terrain/2/0/2.png
## Source : http://tile.stamen.com/terrain/2/1/2.png
## Source : http://tile.stamen.com/terrain/2/2/2.png
## Source : http://tile.stamen.com/terrain/2/3/2.png
## Source : http://tile.stamen.com/terrain/2/4/2.png
## Not Found (HTTP 404). Failed to aquire tile /terrain/2/4/2.png.
ggmap(world_map) +
geom_point(data = Starbucks,
aes(x = Longitude, y = Latitude, color = `Ownership Type`),
size = .3) +
scale_color_viridis_d() +
theme_map() +
theme(legend.background = element_blank(),
legend.key = element_rect("grey50")) +
labs(title = "Starbucks locations across the world")
## Warning: Removed 1 rows containing missing values (geom_point).
The vast majority of Starbucks franchises are in North America, there are a decent amount in Europe and far-East Asia, there are only a couple in Africa and Australia. An overwhelming number of the Starbucks are either licensed or company owned. Noticeably almost all of the Starbucks in Japan and Korea are Joint Ventures.
twin_cities_map <- get_stamenmap(
bbox = c(left = -93.6406, bottom = 44.8062, right = -92.8922, top = 45.1201),
maptype = "terrain",
zoom = 11)
## Source : http://tile.stamen.com/terrain/11/491/735.png
## Source : http://tile.stamen.com/terrain/11/492/735.png
## Source : http://tile.stamen.com/terrain/11/493/735.png
## Source : http://tile.stamen.com/terrain/11/494/735.png
## Source : http://tile.stamen.com/terrain/11/495/735.png
## Source : http://tile.stamen.com/terrain/11/491/736.png
## Source : http://tile.stamen.com/terrain/11/492/736.png
## Source : http://tile.stamen.com/terrain/11/493/736.png
## Source : http://tile.stamen.com/terrain/11/494/736.png
## Source : http://tile.stamen.com/terrain/11/495/736.png
## Source : http://tile.stamen.com/terrain/11/491/737.png
## Source : http://tile.stamen.com/terrain/11/492/737.png
## Source : http://tile.stamen.com/terrain/11/493/737.png
## Source : http://tile.stamen.com/terrain/11/494/737.png
## Source : http://tile.stamen.com/terrain/11/495/737.png
## Source : http://tile.stamen.com/terrain/11/491/738.png
## Source : http://tile.stamen.com/terrain/11/492/738.png
## Source : http://tile.stamen.com/terrain/11/493/738.png
## Source : http://tile.stamen.com/terrain/11/494/738.png
## Source : http://tile.stamen.com/terrain/11/495/738.png
ggmap(twin_cities_map) +
geom_point(data = Starbucks %>% filter(`State/Province` == "MN"),
aes(x = Longitude, y = Latitude),
color = "#00704A") +
scale_color_viridis_d() +
theme_map() +
theme(legend.background = element_blank()) +
labs(title = "Starbucks locations in the Twin Cities")
## Warning: Removed 74 rows containing missing values (geom_point).
If I zoom out it loads a lot faster but there is less detail. I can’t see where each Starbucks is. Also the city labels are very large, they are almost distorted. The latitude and longitude stay the same, it just zooms in within those limits.
get_stamenmap() in help and look at maptype). Include a map with one of the other map types.twin_cities_map_toner <- get_stamenmap(
bbox = c(left = -93.6406, bottom = 44.8062, right = -92.8922, top = 45.1201),
maptype = "toner-lite",
zoom = 11)
## Source : http://tile.stamen.com/toner-lite/11/491/735.png
## Source : http://tile.stamen.com/toner-lite/11/492/735.png
## Source : http://tile.stamen.com/toner-lite/11/493/735.png
## Source : http://tile.stamen.com/toner-lite/11/494/735.png
## Source : http://tile.stamen.com/toner-lite/11/495/735.png
## Source : http://tile.stamen.com/toner-lite/11/491/736.png
## Source : http://tile.stamen.com/toner-lite/11/492/736.png
## Source : http://tile.stamen.com/toner-lite/11/493/736.png
## Source : http://tile.stamen.com/toner-lite/11/494/736.png
## Source : http://tile.stamen.com/toner-lite/11/495/736.png
## Source : http://tile.stamen.com/toner-lite/11/491/737.png
## Source : http://tile.stamen.com/toner-lite/11/492/737.png
## Source : http://tile.stamen.com/toner-lite/11/493/737.png
## Source : http://tile.stamen.com/toner-lite/11/494/737.png
## Source : http://tile.stamen.com/toner-lite/11/495/737.png
## Source : http://tile.stamen.com/toner-lite/11/491/738.png
## Source : http://tile.stamen.com/toner-lite/11/492/738.png
## Source : http://tile.stamen.com/toner-lite/11/493/738.png
## Source : http://tile.stamen.com/toner-lite/11/494/738.png
## Source : http://tile.stamen.com/toner-lite/11/495/738.png
ggmap(twin_cities_map_toner) +
geom_point(data = Starbucks %>% filter(`State/Province` == "MN"),
aes(x = Longitude, y = Latitude),
color = "#00704A") +
scale_color_viridis_d() +
theme_map() +
theme(legend.background = element_blank()) +
labs(title = "Starbucks locations across the Twin Cities")
## Warning: Removed 74 rows containing missing values (geom_point).
annotate() function (see ggplot2 cheatsheet).ggmap(twin_cities_map_toner) +
geom_point(data = Starbucks %>% filter(`State/Province` == "MN"),
aes(x = Longitude, y = Latitude),
color = "#00704A") +
annotate(geom = "point", x =-93.1691 , y = 44.9379, color = "orange") +
annotate(geom = "text", x =-93.1691 , y = 44.9379 - 0.0075,
label = "Macalester College", color = "orange", size = 3) +
scale_color_viridis_d() +
theme_map() +
theme(legend.background = element_blank()) +
labs(title = "Starbucks locations across the Twin Cities")
## Warning: Removed 74 rows containing missing values (geom_point).
geom_map())The example I showed in the tutorial did not account for population of each state in the map. In the code below, a new variable is created, starbucks_per_10000, that gives the number of Starbucks per 10,000 people. It is in the starbucks_with_2018_pop_est dataset.
census_pop_est_2018 <- read_csv("https://www.dropbox.com/s/6txwv3b4ng7pepe/us_census_2018_state_pop_est.csv?dl=1") %>%
separate(state, into = c("dot","state"), extra = "merge") %>%
select(-dot) %>%
mutate(state = str_to_lower(state))
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## state = col_character(),
## est_pop_2018 = col_double()
## )
starbucks_with_2018_pop_est <-
starbucks_us_by_state %>%
left_join(census_pop_est_2018,
by = c("state_name" = "state")) %>%
mutate(starbucks_per_10000 = (n/est_pop_2018)*10000)
dplyr review: Look through the code above and describe what each line of code does.1 - Loads a csv file from dropbox and renames the resulting data frame ‘census_pop_est_2018’
2 - In the original file, the state names have a dot in front of them, this separates that into a dot variable and a state variable (without the dot). The extra controls what to do if there are too many pieces.
3 - Selects everything except the dot column
4 - Creates a new state column (overwrites the old one), where the state names are now lowercase
5 - blank
6 - Renames the resulting data frame ‘starbucks_with_2018_pop_est’
7 - Tells R to use the ‘starbucks_us_by_state’ data frame
8 - Joins the Starbucks data with the census data from above, by the state name
9 - Creates a new variable ‘starbucks_per_10000’ which is the number of starbucks divided by the population multiplied by 10,000
us_map <- map_data("state")
starbucks_with_2018_pop_est %>%
ggplot() +
geom_map(map = us_map,
aes(map_id = state_name,
fill = starbucks_per_10000)) +
geom_point(data = Starbucks %>% filter(Country == "US", `State/Province` != "HI", `State/Province` != "AK"),
aes(x = Longitude,
y = Latitude),
size = .25) +
expand_limits(x = us_map$long, y = us_map$lat) +
theme_map() +
labs(title = "Number of Starbucks per 10,000 people across the US",
caption = "Visual: Alexander Hopkins",
fill = "Starbucks/10,000") +
scale_fill_viridis_c() +
theme(legend.background = element_blank())
The Western States have more Starbucks per 10,000 people than other parts of the country. The East Coast appears to have a lot of Starbucks but they are spread over different states. West Virginia, Mississippi and Vermont have the fewest Starbucks per 10,000.
leaflet)tibble() function that has 10-15 rows of your favorite places. The columns will be the name of the location, the latitude, the longitude, and a column that indicates if it is in your top 3 favorite locations or not. For an example of how to use tibble(), look at the favorite_stp_by_lisa I created in the data R code chunk at the beginning.fav_plaes <- tibble(
place = c("Home", "Macalester College", "Adams Spanish Immersion",
"Spirit Gymnastics", "Bama & Bapa", "Now Bikes",
"Dance Spectrum", "Pizza Luce", "Brunson's"),
long = c(-93.1405743, -93.1712321, -93.1451796,
-93.1650563, -93.1542883, -93.1696608,
-93.1393172, -93.1524256, -93.0753863),
lat = c(44.950576, 44.9378965, 44.9237914,
44.9654609, 44.9295072, 44.9436813,
44.9399922, 44.9468848, 44.9700727)
)
Create a leaflet map that uses circles to indicate your favorite places. Label them with the name of the place. Choose the base map you like best. Color your 3 favorite places differently than the ones that are not in your top 3 (HINT: colorFactor()). Add a legend that explains what the colors mean.
Connect all your locations together with a line in a meaningful way (you may need to order them differently in the original data).
If there are other variables you want to add that could enhance your plot, do that now.
This section will revisit some datasets we have used previously and bring in a mapping component.
The data come from Washington, DC and cover the last quarter of 2014.
Two data tables are available:
Trips contains records of individual rentalsStations gives the locations of the bike rental stationsHere is the code to read in the data. We do this a little differently than usualy, which is why it is included here rather than at the top of this file. To avoid repeatedly re-reading the files, start the data import chunk with {r cache = TRUE} rather than the usual {r}. This code reads in the large dataset right away.
data_site <-
"https://www.macalester.edu/~dshuman1/data/112/2014-Q4-Trips-History-Data.rds"
Trips <- readRDS(gzcon(url(data_site)))
Stations<-read_csv("http://www.macalester.edu/~dshuman1/data/112/DC-Stations.csv")
##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## name = col_character(),
## lat = col_double(),
## long = col_double(),
## nbBikes = col_double(),
## nbEmptyDocks = col_double()
## )
Stations to make a visualization of the total number of departures from each station in the Trips data. Use either color or size to show the variation in number of departures. This time, plot the points on top of a map. Use any of the mapping tools you’d like.dc_map <- get_stamenmap(
bbox = c(left = -77.4032, bottom = 38.7319, right = -76.6547, top = 39.0771),
maptype = "terrain",
zoom = 11)
## Source : http://tile.stamen.com/terrain/11/583/782.png
## Source : http://tile.stamen.com/terrain/11/584/782.png
## Source : http://tile.stamen.com/terrain/11/585/782.png
## Source : http://tile.stamen.com/terrain/11/586/782.png
## Source : http://tile.stamen.com/terrain/11/587/782.png
## Source : http://tile.stamen.com/terrain/11/583/783.png
## Source : http://tile.stamen.com/terrain/11/584/783.png
## Source : http://tile.stamen.com/terrain/11/585/783.png
## Source : http://tile.stamen.com/terrain/11/586/783.png
## Source : http://tile.stamen.com/terrain/11/587/783.png
## Source : http://tile.stamen.com/terrain/11/583/784.png
## Source : http://tile.stamen.com/terrain/11/584/784.png
## Source : http://tile.stamen.com/terrain/11/585/784.png
## Source : http://tile.stamen.com/terrain/11/586/784.png
## Source : http://tile.stamen.com/terrain/11/587/784.png
trip_station <- Trips %>%
group_by(sstation) %>%
summarise(num_departures = n()) %>%
left_join(Stations, by = c("sstation" = "name"))
ggmap(dc_map) +
geom_point(data = trip_station,
aes(x = long, y = lat, color = num_departures), size = 1) +
scale_color_viridis_c(option = "inferno") +
theme_map() +
theme(legend.background = element_blank()) +
labs(title = "Number of departures from each station",
x = "",
y = "",
color = "Number of Departures")
## Warning: Removed 32 rows containing missing values (geom_point).
trip_station_prop <- Trips %>%
group_by(sstation, client) %>%
summarise(num_departures = n()) %>%
mutate(total_departures = sum(num_departures),
percent_casual = ifelse(client == "Casual", num_departures/total_departures, 0)) %>%
filter(percent_casual != 0) %>%
left_join(Stations, by = c("sstation" = "name"))
## `summarise()` has grouped output by 'sstation'. You can override using the `.groups` argument.
ggmap(dc_map) +
geom_point(data = trip_station_prop,
aes(x = long, y = lat, color = percent_casual), size = 1) +
scale_color_viridis_c(option = "inferno") +
theme_map() +
theme(legend.background = element_blank()) +
labs(title = "Number of departures from each station",
x = "",
y = "",
color = "Number of Departures")
## Warning: Removed 32 rows containing missing values (geom_point).
The locations with the highest proportion of casual riders are all around the National Mall. This suggests that they could be tourists, borrowing the bikes for a day of site seeing.
The following exercises will use the COVID-19 data from the NYT.
options(scipen = 7)
covid19 %>%
group_by(state) %>%
mutate(state = str_to_lower(state)) %>%
filter(date == max(date)) %>%
ggplot() +
geom_map(map = us_map,
aes(map_id = state,
fill = cases)) +
expand_limits(x = us_map$long, y = us_map$lat) +
theme_map() +
labs(title = "COVID 19 Cases by State",
fill = "") +
scale_fill_viridis_c() +
theme(legend.background = element_blank())
The problem with this map is it is not weighted by population. The biggest states (California, Texas) have more cases, but a lot of this is becasue there are more people living in those states.
options(scipen = 7)
covid_with_2018_pop_est <-
covid19 %>%
group_by(state) %>%
mutate(state = str_to_lower(state)) %>%
filter(date == max(date)) %>%
left_join(census_pop_est_2018, by = "state") %>%
mutate(cases_per_10000 = (cases/est_pop_2018)*10000)
covid_with_2018_pop_est %>%
ggplot() +
geom_map(map = us_map,
aes(map_id = state,
fill = cases_per_10000)) +
expand_limits(x = us_map$long, y = us_map$lat) +
theme_map() +
labs(title = "COVID19 cases per 10,000 by state",
fill = "") +
scale_fill_viridis_c() +
theme(legend.background = element_blank())
These exercises use the datasets MplsStops and MplsDemo from the carData library. Search for them in Help to find out more information.
MplsStops dataset to find out how many stops there were for each neighborhood and the proportion of stops that were for a suspicious vehicle or person. Sort the results from most to least number of stops. Save this as a dataset called mpls_suspicious and display the table.mpls_suspicious <- MplsStops %>%
group_by(neighborhood, problem) %>%
summarize(num = n()) %>%
pivot_wider(id_cols = neighborhood:num,
names_from = "problem",
values_from = "num") %>%
mutate(total_stops = suspicious+traffic,
prop_sus = suspicious/total_stops) %>%
arrange(desc(total_stops))
## `summarise()` has grouped output by 'neighborhood'. You can override using the `.groups` argument.
mpls_suspicious
Use a leaflet map and the MplsStops dataset to display each of the stops on a map as a small point. Color the points differently depending on whether they were for suspicious vehicle/person or a traffic stop (the problem variable). HINTS: use addCircleMarkers, set stroke = FAlSE, use colorFactor() to create a palette.
Save the folder from moodle called Minneapolis_Neighborhoods into your project/repository folder for this assignment. Make sure the folder is called Minneapolis_Neighborhoods. Use the code below to read in the data and make sure to delete the eval=FALSE. Although it looks like it only links to the .sph file, you need the entire folder of files to create the mpls_nbhd data set. These data contain information about the geometries of the Minneapolis neighborhoods. Using the mpls_nbhd dataset as the base file, join the mpls_suspicious and MplsDemo datasets to it by neighborhood (careful, they are named different things in the different files). Call this new dataset mpls_all.
mpls_nbhd <- st_read("Minneapolis_Neighborhoods/Minneapolis_Neighborhoods.shp", quiet = TRUE)
mpls_all <- MplsDemo %>%
left_join(mpls_suspicious, by = "neighborhood") %>%
left_join(mpls_nbhd, by = c("neighborhood" = "BDNAME"))
Use leaflet to create a map from the mpls_all data that colors the neighborhoods by prop_suspicious. Display the neighborhood name as you scroll over it. Describe what you observe in the map.
Use leaflet to create a map of your own choosing. Come up with a question you want to try to answer and use the map to help answer that question. Describe what your map shows.
DID YOU REMEMBER TO UNCOMMENT THE OPTIONS AT THE TOP?